Smart Agriculture System for Plant Disease Detection and Irrigation Management Using Machine Learning and IoT

Food security and crop productivity are seriously threatened by plant diseases, which calls for early identification and treatment. Researchers have been working for farmers using smart agriculture systems based on the Internet of Things (IoT) for years. They demonstrated a number of disease classification models, highlighting the applications of radial basis function and convolutional neural networks (CNNs), This study presents a comprehensive Smart Agriculture System for Plant Disease Detection aimed at minimizing damage and curbing disease spread. Leveraging advanced technologies encompassing machine learning, computer vision, and IoT sensors, the system monitors crop health in real time. Its design facilitates automated disease detection, outbreak prediction, and treatment recommendation. The system's foundation on image processing for disease detection and IoT integration for precise irrigation management encompasses image acquisition, segmentation, feature extraction, machine learning, decision-making algorithms, and data analysis. Furthermore, the results validate the efficacy of the system in disease detection and irrigation control, while acknowledging the need for further refinement. After successful integration of Raspberry Pi, NodeMCU, sensors, and motor pump, the study provides essential data tables that clarify optimal environmental conditions for different crops and the comparative precision of disease detection methods. The mobile application of the prototype facilitates monitoring and diagnosis. As the agricultural landscape evolves toward Industry 5.0, this study contributes to a sustainable, technology-driven future where smart agriculture harmonizes human expertise and technological innovation.